Multivariate data analysis for outcome studies

Publisher Website
Google Scholar
Abstract
The use of multivariate statistical techniques for analyzing the complex data often gathered in outcome studies is discussed. The multivariate analysis of variance (MANO VA) is suggested for multiple group studies common to outcome studies. This technique can be utilized for a large number of specific research designs whenever multiple outcome measures are collected. MANOVA offers two specific advantages over more familiar univariate approaches: It presents better control over Type 1 error rates while preserving statistical power, and it allows more thorough analysis of complex data. Outcome studies are frequently conducted in evaluation and field research to ascertain the effects of treatments or programs on individuals. Basically, their focus is upon changes on a criterion or criteria as a function of participation in a treatment or program. These studies are found in all areas of human services from mental health to education, and regardless of content area they share a similar basic methodology, albeit with often vastly different instrumentation. As more and more outcome studies have been conducted, it has become increasingly apparent that many, if not most, programs and treatments have multiple effects which can only be reflected by complex criteria. In other words, outcomes tend to be multidimensional, requiring the use of multivariate data to capture fully their complexity. Furthermore, the optimal analysis of multivariate data requires the use of multivariate statistical techniques. Although these techniques are becoming widely known in some areas, the evaluation literature has seemed to focus more on experimental design and measurement issues than data analysis.